What it does
The server exposes visual regression and snapshot testing to AI agents. According to the publisher, an agent can list test runs, read semantic diffs between snapshots and review the results.
It would be reached for when an agent needs to check whether a user interface has changed visually between runs, and to inspect what changed rather than only whether something changed. The publisher's description is brief, so this entry does not describe further workflows.
The source does not state what setup or account the server requires, so running it is not described here beyond its listed capabilities.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
dev.dungbeetle/mcp
Visual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.
v0.1.0As shown on registry.modelcontextprotocol.io when we last read it